Upload 13 files

README.md

@@ -6,7 +6,7 @@ datasets:
 metrics:
 - rouge
 model-index:
-- name: small-2-2-t
+- name: small-2-2
   results:
   - task:
       name: Summarization
@@ -26,9 +26,9 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# small-2-2-t
+# small-2-2
 
-This model is a fine-tuned version of [asy/cnndm/small-2-2](https://huggingface.co/asy/cnndm/small-2-2) on the cnn_dailymail 3.0.0 dataset.
+This model is a fine-tuned version of [cnn/small-2-2/](https://huggingface.co/cnn/small-2-2/) on the cnn_dailymail 3.0.0 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.3258
 - Rouge1: 30.7931

all_results.json

@@ -6,13 +6,13 @@
     "eval_rouge2": 11.9653,
     "eval_rougeL": 22.8812,
     "eval_rougeLsum": 28.0315,
-    "eval_runtime": 1112.339,
+    "eval_runtime": 1159.4563,
     "eval_samples": 13368,
-    "eval_samples_per_second": 12.018,
-    "eval_steps_per_second": 3.004,
+    "eval_samples_per_second": 11.53,
+    "eval_steps_per_second": 2.882,
     "train_loss": 2.94373551809623,
-    "train_runtime": 13417.163,
+    "train_runtime": 13292.9605,
     "train_samples": 287113,
-    "train_samples_per_second": 64.197,
-    "train_steps_per_second": 1.003
+    "train_samples_per_second": 64.797,
+    "train_steps_per_second": 1.012
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "asy/cnndm/small-2-2",
+  "_name_or_path": "cnn/small-2-2/",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

eval_results.json

@@ -6,8 +6,8 @@
     "eval_rouge2": 11.9653,
     "eval_rougeL": 22.8812,
     "eval_rougeLsum": 28.0315,
-    "eval_runtime": 1112.339,
+    "eval_runtime": 1159.4563,
     "eval_samples": 13368,
-    "eval_samples_per_second": 12.018,
-    "eval_steps_per_second": 3.004
+    "eval_samples_per_second": 11.53,
+    "eval_steps_per_second": 2.882
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 2.94373551809623,
-    "train_runtime": 13417.163,
+    "train_runtime": 13292.9605,
     "train_samples": 287113,
-    "train_samples_per_second": 64.197,
-    "train_steps_per_second": 1.003
+    "train_samples_per_second": 64.797,
+    "train_steps_per_second": 1.012
 }

trainer_state.json

@@ -168,9 +168,9 @@
       "step": 13458,
       "total_flos": 1.426727685349294e+17,
       "train_loss": 2.94373551809623,
-      "train_runtime": 13417.163,
-      "train_samples_per_second": 64.197,
-      "train_steps_per_second": 1.003
+      "train_runtime": 13292.9605,
+      "train_samples_per_second": 64.797,
+      "train_steps_per_second": 1.012
     }
   ],
   "max_steps": 13458,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc38728be823bce3a4a2c488eb221fce0cd1df2136324b8de5126fe55847872
-size 3643
+oid sha256:5da0b67532495c165c4068406f1250347eabe634cef5183ef15ddb8870e1ba26
+size 3707